PhD Research Intern — Learned End-to-End Driving and Actuation

You will own one research direction on the production planner, working with the researchers who ship it, on real fleet data, and present your results to the people who decide what ships. What a successful planner means to us, and what we will measure you against:

• Understands what is missing: finds the mechanism behind a driving planner's failures and shows which gap matters before changing anything.
• Handles the long tail, never gets stuck and knows how to get itself unstuck: agile, it commits, launches, re-plans and recovers on its own.
• Collision- and comfort-aware, and generalizes across structured environments (roads, lanes, intersections) and unstructured ones (lots, yards, sites, robotics settings).
• Knows how to test and evaluate actuation and planning pipelines: open-loop, closed-loop and on-vehicle, with metrics that predict road behavior.
• Production quality, not a proof of concept: tested code, reproducible results, behavior that holds across checkpoints and scenes. This is our standard and our measure of success.

• Generative planning with flow matching: a flow-matching or diffusion policy over ego trajectories with few-step inference and explicit constraint guidance in the sampler.
• The long tail: data balancing and hard-case mining, counterfactual and generative scenario synthesis, or reasoning-augmented planners.
• Closed-loop evaluation and training that matches our sensors: counterfactual observations faithful to radar and camera features, so closed-loop metrics predict road behaviour.
• Post-training with reinforcement learning: rule-reward or closed-loop fine-tuning, parallel imitation + RL—and whether the gain survives a real sensor stack and a safety layer.
• Your own idea: tokenized planning with learned scoring, a world model as the planner's critic, uncertainty-aware ranking, self-play traffic.

Every change is evaluated closed-loop and open-loop against the current planner, failures examined and not just counted, and results presented to the team's leads. We support publication of non-proprietary findings.

• Final-year PhD student (or within 12 months of defending) in computer science, electrical engineering, robotics or a related field, available for an on-site internship in Berkeley.
• First-author work in motion forecasting or planning, generative models for sequential decision making (diffusion, flow matching), reinforcement or imitation learning for control, or closed-loop simulation and evaluation.
• Python and PyTorch: you can read a large model file, change the loss, and prove it did what you intended; a solid grasp of the ML pipeline end to end, including real sensor data and its problems.
• Communication, teamwork and brainstorming matter to us as much as the technical bar: work in the open, take and give review well, bring half-formed ideas to the whiteboard early. Research here is a team sport.

• Publications at CVPR, ICCV, ECCV, NeurIPS, ICLR, ICRA, CoRL or RSS on end-to-end driving, trajectory generation, world models or RL post-training.
• Results on a closed-loop benchmark (Bench2Drive, NAVSIM v2, Waymo Sim Agents, nuPlan), and an opinion on where those benchmarks mislead.
• Radar, lidar or multi-sensor BEV perception; multi-day GPU-cluster training kept honest (checkpoint variance, clean ablations); vision-language-action models or constraint-guided sampling.